Image classification, including object recognition and scene classification, remains to be a major challenge to the computer vision community. As machine can be able to extract information from an image and classify it in order to solve some tasks. Recently SVMs using Spatial Pyramid Matching (SPM) kernel have been highly successful in image classification. Despite its popularity, this technique cannot handle more than thousands of training images. In this paper we develop an extension of the SPM method, by generalizing Vector Quantization to Sparse Coding followed by multi-scale Spatial Max Pooling, and also propose a large scale linear classifier based on Scale Invariant Feature Transform (SIFT) and Sparse Codes. This new adapted algorithm remarkably can handle thousands of training images and classify them into different categories.