I. Introduction
Nowadays, many applications in real world deal with massive data stored as images. These may include various multimedia systems, content-based search engines, pattern recognition etc. Fetching multiple images similar to a query image given by user requires automated systems referred to as content based image retrieval (CBIR)systems. The images are compared in terms of similarity by extracting a relevant feature set from the images. In this regard, a number of features have been investigated in the literature. Information from local intensity variations around a pixel are captured by pattern-based features, allowing them to represent all local patterns present in an image.