With the onslaught of multimedia in the near past, there has been a tremendous increase in the uses of images. A very good example of which is the web on which most of the documents contain images. Other than this the images are being used in other applications like weather forecasting, medical diagnosis, police department. In R-Tree implementation of image database, images are made available to the program which are then stores in the database. The image database is presented using R-tree and the database is stored in separate file .This R-tree implementation results in both update as well as efficient retrieval of images from hard disk. We use the similarity based retrieval feature to retrieve the required number of similar images being inquired by the user. Distance matrix approach is used to find similarity of images. Sobel edge detection algorithm is used to form sketches. If sketch of image is entered for similarity based retrieval, then sketches of stored images are formedand these sketches are compared with input image (sketch) using distance matrix approach.