The ability to efficiently manage and analyze large collections of digital images hinges on the effectiveness of the indexing methods used. Effective indexing simplifies image retrieval by generating textual descriptions or digital signatures derived from the visual features of the images, such as color, shape, and texture. These methods significantly improve the accessibility and usability of large image databases. This study explores a new strategy for automatic image indexing, using a content-based image retrieval (CBIR) system. Unlike traditional methods that rely on manual or keyword-based indexing, CBIR focuses on the actual content of the images. By analyzing and indexing visual elements directly, CBIR offers a more accurate and scalable approach to image retrieval, especially for extensive image collections. Automatic image indexing based on CBIR has broad applications across numerous industries. It is particularly beneficial for managing photographic archives, streamlining archive management, and enhancing product searches in e-commerce. Additionally, it can be used in social media platforms to help categorize products, identify inappropriate content, and ensure safer user experiences. The automatic indexing process not only improves the speed and efficiency of image searches but also enhances product classification accuracy. This approach represents a significant advancement in how digital images are organized, accessed, and utilized across various sectors.