Problem statement: as the network and development of multimedia technologies are becoming more popular, users are not satisfied with the traditional information retrieval techniques. so nowadays the content based image retrieval are becoming a source of exact and fast retrieval. in the past few years, immense improvement was obtained in the field of content-based image retrieval (cbir). nevertheless, existing systems still fail when applied to medical image databases. simple feature-extraction algorithms that operate on the entire image for characterization of color, texture, or shape cannot be related to the descriptive semantics of medical knowledge that is extracted from images by human experts. also a correct segmentation of structures is crucial in many medical applications, e.g. diagnosis, surgical planning, simulation and training. approach: in this study, we present a approach called expectation maximization (em) segmentation, gustafson kessel classifier combined with relevance feedback for the retrieval of kidney stone from ultrasound (us) images is introduced. this system can be used to discriminate the abnormal and normal kidney. the diagnosis scheme includes six steps: image registration, feature extraction, feature selection, classification, and image retrieval. first the ultrasound images are pre-processed and filtered. during filtering of images the speckle noise present in ultrasound image is filtered using three different filters namely median filter, wiener filter, gaussian filter and the snr value is obtained for each filter. based on the snr value obtained gaussian is chosen as the best filter to reduce the noise present. thus the gaussian output is used as the input for next step. then the features, derived from (glcm) and gabor feature, are obtained from the pathology bearing regions (pbrs) among the normal and abnormal ultrasound images. the feature selection selects the certain features for the specific diseases and also reduces dimensionality space for classification. finally, we implement our approach for retrieval of specific image from the database. results: this approach can get the query from user and has retrieved both positive and negative samples from the database, by getting feedback in each round from the radiologist is help to improve the retrieval of correct images. conclusion: the gaussian filter reduces the speckle noise present in us image. the approach gk comprises several benefits when compared to existing cbir for medical system. glcm, gabor in feature extraction plays crucial role in ultrasound kidney image retrieval. image registration plays an important role in the retrieval. it reduces the redundancy of retrieval images and increases the response rate.