In modern sciences and technologies, images gain much broader scopes due to the ever growing importance of scientific visualization. The search for similar images in large-scale image databases has been an active research area in the last couple of years. A very promising approach is content based image retrieval (CBIR). Content-Based Image Retrieval (CBIR) is a technique that uses image visual features such as color, texture, shape etc. to retrieve the images from set of large image database according to user’s request which is in the form of query image. The combination of Color and Texture information have been the most important property of any image and provides robust feature set for image retrieval. The information gained by feature extraction is used to measure the similarity between two images. For the comparison of query image and the database image, similarity measures such as Euclidean Distance, Jeffrey Divergence, color histogram matching etc. are used. In this paper, we have used the enhanced entropy feature which works best for textures with small variances and thus improving retrieval results from existing entropies.