there are many tools to check plagiarism checkers like siteliner , duplichecker , plagarism detector, copyscape , small seo tools and so many.
but I think checking plagiarism for 50,000 pages can not do it manually obviously
you can for some paid options otherwise , you can go for Google API Installed on your website which will automatically check similar content.
or maybe have some research about whether is there any script for checking plagiarised content that you can add so that similar content will be auto-deleted.
Bookmarks