In the dynamic landscape of twenty-first century scientific research, the relentless surge of new bulletin through daily article publications presents a noteworthy challenge for researchers striving to stay informed within their domains. Conventional approaches like keyword matching and existing recommender systems have proven to be inefficient, especially when dealing with massive datasets featuring millions of scientific papers. This work introduces an innovative, scalable, end-to-end content-based recommendation system for scientific papers. The scope involves creating a content-based recommendation system for scientific papers to tackle information overload. This system will use index-based or keyword-based to suggest relevant articles, making it easier for researchers to access pertinent works. Additionally, it aims to foster interdisciplinary exploration by identifying thematic connections, contributing to scientific advancement and understanding. Unlike prior methods, our system employs the index or title of a given paper to recommend relevant research papers, promising a more precise and pertinent selection. This breakthrough has the potential to transform how researchers discover valuable articles, effectively mitigating information overload and ensuring that groundbreaking studies receive the attention they deserve. Our comprehensive system achieves an average response time of 1.45 s and shows the results with the use of cosine similarity makes the system more effective which checks the similar titles and recommends them.