Due to the development and improvement in internet with high speed for the last few years andthe availability of a large digital image collection, efficient image retrieval systems are required. Retrievalcan be text-based and content-based. In content-based, which is also called Content-Based Image retrieval(CBIR), low level features of images are extracted such as color, texture and shape. These features areused in similarity measurement to retrieve relevant images from an image database. A CBIR algorithm isproposed which is based on the color histogram using Laplacian filter to reduce the noise and provides anenhanced image with more detail informations. Color histogram of the filtered image is divided into bins.Mean and standard deviation are calculated for pixels in each bin to get feature vector which is used forimage retrieval. After various experiments with user queries, results show the good retrieval of images byalgorithm. © 2005 - 2011 JATIT & LLS.